Quantitative Methods for Food Systems Research

Quantitative Methods

What are they good for
What are they not good for
Standard toolkit
- Regression and friends
building on that
- directed acyclic graphs
- structural equation model
system modeling:
- fuzzy cognitive mapping
- agent-based
- system dynamics
bayesian methods

A picture of a field at Intervale Farm. — Intervale Farm, Sally McCay, UVM Photo

What does a p-value mean? (Anderson 2020)
- Should be smaller

Berksen’s paradox
Image of a DAG, chain collider

Misinterpretation of confidence intervals (Cumming and Finch 2005)

Illusion of Predictability in Scientific Results (Zhang et al. 2023)
What is the effect size?

People misunderstand graphs

{r}

plot(iris)

Approaching a Quantitative Analysis

Plan Ahead
Choosing Tools
EDA
Reproducibility
Version Control

Power, sample size, outliers, analyses
Think many analyses
consider preregistration
DAGs asnd Berksen

do it
distributional assumptions
missing data, unknown trends

Reproducibility
Version Control

Do it

References

Anderson, Samantha F. 2020. “Misinterpreting p: The Discrepancy Between p Values and the Probability the Null Hypothesis Is True, the Influence of Multiple Testing, and Implications for the Replication Crisis.” Psychological Methods 25 (5): 596–609. https://doi.org/10.1037/met0000248.

Cumming, Geoff, and Sue Finch. 2005. “Inference by Eye: Confidence Intervals and How to Read Pictures of Data.” American Psychologist 60 (2): 170–80. https://doi.org/10.1037/0003-066X.60.2.170.

Zhang, Sam, Patrick R. Heck, Michelle N. Meyer, Christopher F. Chabris, Daniel G. Goldstein, and Jake M. Hofman. 2023. “An Illusion of Predictability in Scientific Results: Even Experts Confuse Inferential Uncertainty and Outcome Variability.” Proceedings of the National Academy of Sciences 120 (33): e2302491120. https://doi.org/10.1073/pnas.2302491120.